This repository contains files for automated soil sampling selection using the K-Means algorithm. The files in this repository include:
-
Data preparation: This file contains code for preparing the data for analysis, including cleaning and preprocessing steps.
-
Outliers removal: This file contains code for identifying and removing outliers from the data.
-
Unsupervised sampling selection: This file contains code for selecting soil samples using the K-Means algorithm.
Notes: The covariates used in the script are commonly from Sentinel 2A-MSI spectral indices, DEM, and Landsat 8 OLI. The unsupervised K-Means technique used in this repository was derived from Brus (2019).
Brus, D. J. (2019). Sampling for digital soil mapping: A tutorial supported by R scripts. Geoderma, 338, 464-480. https://doi.org/10.1016/j.geoderma.2018.07.036